Diagnosis Support Model of Cardiomegaly Based on CNN Using ResNet and Explainable Feature Map

Yoo, Hana; Han, Soyoung; Chung, Kyungyong

doi:10.1109/access.2021.3068597

Cited by 19 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Cardiomegaly was diagnosed using CNN and explainable feature map for explainability with CXR images [236]. CXR images were used for cardiac hyper-trophy readings [236]. Functional accuracy of CNN was used for model evaluation [236].…”

Section: Conventional Imaging/x-raysmentioning

confidence: 99%

“…CXR images were used for cardiac hyper-trophy readings [236]. Functional accuracy of CNN was used for model evaluation [236]. The feature map showed positive values for the portions with significant influence on the disease diagnosis [236].…”

Section: Conventional Imaging/x-raysmentioning

confidence: 99%

“…Functional accuracy of CNN was used for model evaluation [236]. The feature map showed positive values for the portions with significant influence on the disease diagnosis [236]. Five deep CNN models were used for automatic classification of paediatric musculoskeletal radiographs of the five anatomical area (shoulder, elbow, pelvis, hand, and knee) and achieved a classification rate of 33 radiographs per second [235].…”

Section: Conventional Imaging/x-raysmentioning

confidence: 99%

See 2 more Smart Citations

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Nazir¹,

Dickson²,

Akram³

2023

Computers in Biology and Medicine

101

View full text Add to dashboard Cite

Section: Conventional Imaging/x-raysmentioning

confidence: 99%

Section: Conventional Imaging/x-raysmentioning

confidence: 99%

Section: Conventional Imaging/x-raysmentioning

confidence: 99%

See 1 more Smart Citation

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Nazir¹,

Dickson²,

Akram³

2023

Computers in Biology and Medicine

101

View full text Add to dashboard Cite

“…Their superior capabilities against the numerous traditional statistical approaches for hand-crafted feature extraction are quite commendable since they are capable of extracting both discriminative and prognosible features at multiple levels [5,6]. For instance, with the aid of convolving filters and deep multi-layers, convolutional neural networks (CNNs) are capable of deep feature learning in supervised cases-image recognition [7], fault diagnostics [8], anomaly detection, etc. [9].…”

Section: Introductionmentioning

confidence: 99%

A CEEMDAN-Assisted Deep Learning Model for the RUL Estimation of Solenoid Pumps

Akpudo¹,

Hur²

2021

Electronics

View full text Add to dashboard Cite

This paper develops a data-driven remaining useful life prediction model for solenoid pumps. The model extracts high-level features using stacked autoencoders from decomposed pressure signals (using complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm). These high-level features are then received by a recurrent neural network-gated recurrent units (GRUs) for the RUL estimation. The case study presented demonstrates the robustness of the proposed RUL estimation model with extensive empirical validations. Results support the validity of using the CEEMDAN for non-stationary signal decomposition and the accuracy, ease-of-use, and superiority of the proposed DL-based model for solenoid pump failure prognostics.

show abstract

“…In this regard, high accuracy and fast judgment are influenced by data evaluated and algorithms applied. Therefore, the use of a good assisted-diagnosis technology based on AI is expected to improve this process [4], [5]. To apply AI to the diagnosis of a disease and the detection of lesions, which are abnormal changes in the tissue of an organism, a model is required to understand the disease [40]- [42].…”

Section: Introductionmentioning

confidence: 99%

PGGAN-Based Anomaly Classification on Chest X-Ray Using Weighted Multi-Scale Similarity

2021

Self Cite

View full text Add to dashboard Cite

To use artificial intelligence to assist in diagnoses applications, a model to utilize quality data is required, which results in massive time and cost. In medical data, data imbalance occurs because the amount of data with lesions is less than that without lesions. To overcome this limitation, this study proposes a progressive growth of generative adversarial networks (PGGAN)-based anomaly classification on chest Xrays using weighted multi-scale similarity. An anomaly detection method is applied to learn the distribution of normal images to solve the problem of data imbalance. The use of PGGAN, which is a model that generates high-resolution images by gradually adding layers, enables to find image characteristics on a multi-scale and define the similarity between an original image and a generated image. The anomaly score is calculated by applying the weighted arithmetic mean to a resolution-by-resolution similarity. The threshold is defined after the analysis of the F1-score, and then the classification performance is evaluated. The accuracy of the proposed model was assessed using a confusion matrix and compared with that of a conventional classification model, and the efficiency was demonstrated through ablation studies. The classification accuracy of the test dataset was 0.8525. Compared to a U-net-based disease classifier with low-resolution which accuracy was 0.8410, the performance of the proposed model was 0.8507, exhibited an improvement.

show abstract

Diagnosis Support Model of Cardiomegaly Based on CNN Using ResNet and Explainable Feature Map

Cited by 19 publications

References 33 publications

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

A CEEMDAN-Assisted Deep Learning Model for the RUL Estimation of Solenoid Pumps

PGGAN-Based Anomaly Classification on Chest X-Ray Using Weighted Multi-Scale Similarity

Contact Info

Product

Resources

About